Audio-to-Audio
Transformers
Safetensors
llama
audio
audio-language-model
speech-recognition
text-to-speech
speech-conversation
text-generation-inference
Instructions to use maitrix-org/Voila-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use maitrix-org/Voila-base with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("maitrix-org/Voila-base") model = AutoModel.from_pretrained("maitrix-org/Voila-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from maitrix-org/Voila-base: direct link, hf CLI and curl.
- Browser
- Download file 822 Bytes
-
https://huggingface.co/maitrix-org/Voila-base/resolve/main/config.json
- Command line
-
hf download hf://maitrix-org/Voila-base/config.json
-
curl -L -o config.json https://huggingface.co/maitrix-org/Voila-base/resolve/main/config.json
822 Bytes
| { | |
| "architectures": [ | |
| "VoilaModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "audio_token_id": 136457, | |
| "bos_token_id": 128000, | |
| "codebook_size": 2048, | |
| "eos_token_id": 128001, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_audio_token_id": 136447, | |
| "max_position_embeddings": 4096, | |
| "min_audio_token_id": 128256, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_codebooks": 4, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.49.0", | |
| "use_cache": true, | |
| "vocab_size": 136512 | |
| } | |